advertisement
Automated detection of eyes with a high risk of early glaucoma with high specificity could make screening or risk stratification possible. This is especially important in earlier stages of the disease so that further functional damage may be prevented.1
Mohammadzadeh et al. proposed using novel parameters from optical coherence tomography macular volume scans to discriminate perimetric glaucoma from healthy subjects. Parameters developed based on cubic Bezier curves were used from macular topography and the performance of these parameters on glaucoma detection was evaluated. This approach has been used recently for differentiating between neuromyelitis optica and multiple sclerosis,2 and also healthy subjects and patients with inflammatory optic neuropathies.3
Sensitivity, specificity, and AUC for discriminating between healthy and glaucoma eyes were 81.5% (95% CI = 76.6‐91.9%), 89.7% (95% CI = 78.7‐94.2%), and 0.915 (95% CI = 0.882‐0.948), respectively. Using machine learning approach temporal inferior rim height, nasal inferior pit volume, and temporal pit depth were the top three shape measures with an AUC of 0.915 for discriminating eyes with glaucoma of various stages from healthy eyes.
However, most of the glaucoma patients were moderate to advanced glaucoma with an average mean deviation of −8.2 ± 6.1 dB. The results need to be confirmed in a larger study and potentially in eyes with preperimetric glaucoma. In addition, variability in the macula shape and thickness has been reported previously, especially among different races.4 Macula shape is also affected by axial length. Therefore, a larger normal database is required to define the factors potentially affecting shape parameters and their performance in glaucoma detection.
In summary, macular shape biomarkers detect early glaucoma with clinically relevant performance. The proposed biomarkers are not dependent on the segmentation of individual retinal layers and may be especially helpful when accurate segmentation of the inner retinal layers cannot be achieved. Future studies are needed to explore the utility of these parameters in the monitoring of disease in glaucoma patients.